DeepSeek V4-Flash Vision RAG lets AI truly understand a PDF, then answer your questions, tell you which page contains the answer, and display the original page image for verification. A PDF deep question-answering and retrieval (vision RAG) Agent Skill based on the DeepSeek vision model deepseek-v4-flash-vision-exp. Supports both text-based and scanned PDFs, and understands charts, tables, code blocks, and formulas—not just text.
liangdabiao/deepseek-v4-flash-vision-rag
Skill Claude CodeCodex
A PDF question-answering and search tool that can understand text, scanned pages, charts, tables, and code. It can point to physical page numbers, quote matching text, and show page images.